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. Our dataset is publicly available at: https://github.com/menamerai/cheer-ekman.
@article{arxiv.2506.01047,
title = {CHEER-Ekman: Fine-grained Embodied Emotion Classification},
author = {Phan Anh Duong and Cat Luong and Divyesh Bommana and Tianyu Jiang},
journal= {arXiv preprint arXiv:2506.01047},
year = {2025}
}