Emotion recognition benchmarks predict one emotion per text, missing many real-world scenarios where two people arrive at opposing emotions from a single shared trigger. For example, a child kicks her seat in excitement while the passenger ahead feels mounting irritation. We introduce Chiaro, a 1,000 human-annotated sentence benchmark for contrastive emotion inference grounded in appraisal theory. Each scene describes one causal trigger eliciting a positive emotion in one person and a negative emotion in the other, drawn from a ten-class taxonomy. We benchmark seven frontier LLMs and four off-the-shelf emotion classifiers, where the strongest LLM reaches 67.3 macro-F1, well below human agreement, while existing emotion classifiers score near chance. Beyond evaluation, Chiaro also serves as a training signal: combined with an existing emotion corpus, the resulting downstream classifier improves on Chiaro itself and on six of ten external emotion benchmarks, positioning Chiaro as a complementary signal for emotion recognition.

Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied. We present an embodied emotion classification dataset, CHEER-Ekman, extending the existing binary embodied emotion dataset with Ekman’s six basic emotion categories. Using automatic best-worst scaling with large language models, we achieve performance superior to supervised approaches on our new dataset. Our investigation reveals that simplified prompting instructions and chain-of-thought reasoning significantly improve emotion recognition accuracy, enabling smaller models to achieve competitive performance with larger ones.