Large language models are widely used for personal advice (relationship conflicts, financial decisions, mental-health support, etc.), but they often align their response with the user’s position rather than offering independent judgment, even when users need pushback rather than validation. Mitigating this, whether through training objectives, system-level guardrails, or evaluation design, requires knowing what triggers it. But what in the user’s message triggers this behavior is unknown. Natural advice-seeking messages vary simultaneously in semantic content (what is disclosed), linguistic style (how it is written), and narrative framing (whose side is told), but existing benchmarks cannot attribute model behavior to any single cue. Without this attribution, mitigations cannot be targeted, for example, suppressing warmth may harm users with genuine distress but might not fix the model’s tendency to endorse whichever side of a conflict speaks. In this work, we isolate which of these cues drive which aspect of sycophantic behavior across 787 advice-seeking scenarios and observe three patterns emerge: emotional warmth is content-driven; stance endorsement is framing-driven: endorsement drops by ∼50% when the same conflict is retold from the opposing perspective; and recommendation directness is style-driven. We also find that hedging reduces rather than increases model endorsement; models do not simply validate vulnerable-sounding users.

Email conversations are the primary mode of communication in enterprises. The email content expresses an individual’s needs, requirements and intentions. Affective information in the email text can be used to get an insight into the sender’s mood or emotion. We present a novel approach to model human frustration in text. We identify linguistic features that influence human perception of frustration and model it as a supervised learning task. The paper provides a detailed comparison across traditional regression and word distribution-based models. We report a mean-squared error (MSE) of 0.018 against human-annotated frustration for the best performing model. The approach establishes the importance of affect features in frustration prediction for email data. We further evaluate the efficacy of the proposed feature set and model in predicting other tone or affects in text, namely formality and politeness; results demonstrate a comparable performance against the state-of-the-art baselines.