@inproceedings{saini-etal-2026-learning,
title = "Learning Structured Emotional Dynamics in Latent Space via Trajectory Modeling and Controlled Transitions",
author = "Saini, Agampreet and
Abusalameh, Bayan and
Singh, Rahul Kumar and
Cambria, Erik",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1565/",
doi = "10.18653/2026.findings-emnlp.1565",
pages = "33329--33354",
ISBN = "979-8-89176-462-0",
abstract = "Emotion understanding from text has been predominantly approached through discrete classification frameworks. However, complementary perspectives in psychology and neuroscience suggest that affective states may also exhibit continuous, context-dependent, and temporally structured properties. Building on this perspective, we investigate emotion representations as latent dynamical trajectories within transformer embedding spaces. Using GoEmotions and MELD across four transformer architectures, we analyze the geometric organization and temporal evolution of learned emotional states. We find that latent trajectories exhibit temporal persistence and structured transition dynamics, while the prediction error increases during emotion shifts, acting as a signal of expectation violation. We additionally introduce trajectory-level latent interventions enabling controllable emotional transitions through directional operations in representation space. Finally, manifold capacity analysis reveals partially aligned and variably separable emotional manifolds, suggesting shared geometric organization across affective representations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saini-etal-2026-learning">
<titleInfo>
<title>Learning Structured Emotional Dynamics in Latent Space via Trajectory Modeling and Controlled Transitions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agampreet</namePart>
<namePart type="family">Saini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bayan</namePart>
<namePart type="family">Abusalameh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Emotion understanding from text has been predominantly approached through discrete classification frameworks. However, complementary perspectives in psychology and neuroscience suggest that affective states may also exhibit continuous, context-dependent, and temporally structured properties. Building on this perspective, we investigate emotion representations as latent dynamical trajectories within transformer embedding spaces. Using GoEmotions and MELD across four transformer architectures, we analyze the geometric organization and temporal evolution of learned emotional states. We find that latent trajectories exhibit temporal persistence and structured transition dynamics, while the prediction error increases during emotion shifts, acting as a signal of expectation violation. We additionally introduce trajectory-level latent interventions enabling controllable emotional transitions through directional operations in representation space. Finally, manifold capacity analysis reveals partially aligned and variably separable emotional manifolds, suggesting shared geometric organization across affective representations.</abstract>
<identifier type="citekey">saini-etal-2026-learning</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1565</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1565/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33329</start>
<end>33354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Structured Emotional Dynamics in Latent Space via Trajectory Modeling and Controlled Transitions
%A Saini, Agampreet
%A Abusalameh, Bayan
%A Singh, Rahul Kumar
%A Cambria, Erik
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F saini-etal-2026-learning
%X Emotion understanding from text has been predominantly approached through discrete classification frameworks. However, complementary perspectives in psychology and neuroscience suggest that affective states may also exhibit continuous, context-dependent, and temporally structured properties. Building on this perspective, we investigate emotion representations as latent dynamical trajectories within transformer embedding spaces. Using GoEmotions and MELD across four transformer architectures, we analyze the geometric organization and temporal evolution of learned emotional states. We find that latent trajectories exhibit temporal persistence and structured transition dynamics, while the prediction error increases during emotion shifts, acting as a signal of expectation violation. We additionally introduce trajectory-level latent interventions enabling controllable emotional transitions through directional operations in representation space. Finally, manifold capacity analysis reveals partially aligned and variably separable emotional manifolds, suggesting shared geometric organization across affective representations.
%R 10.18653/2026.findings-emnlp.1565
%U https://aclanthology.org/2026.findings-emnlp.1565/
%U https://doi.org/10.18653/2026.findings-emnlp.1565
%P 33329-33354
Markdown (Informal)
[Learning Structured Emotional Dynamics in Latent Space via Trajectory Modeling and Controlled Transitions](https://aclanthology.org/2026.findings-emnlp.1565/) (Saini et al., Findings 2026)
ACL