arXiv:2607. 18691v1 Announce Type: new Abstract: Progresses have been made on understanding emotion mechanisms of large language models (LLMs).
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 26987v1 Announce Type: cross Abstract: Recent work identified emotion vectors in Claude Sonnet 4.
arXiv:2606. 14742v1 Announce Type: cross Abstract: Do LLMs have emotions?
Sofroniew et al. (2026) showed that emotion concepts in Claude Sonnet 4.5 are encoded as vectors whose geometry mirrors human affect psychology. This study replicates that finding using the base pretrained model google/gemma-2-27b, generating 205,200 Claude Sonnet 4.5 stories, extracting 171 emotion vectors, and recovering a similar affective circumplex with principal components explaining comparable variance. The analysis further identifies a sharp geometric seam at layers 22‑26, demonstrates that much of the geometry already exists in static token embeddings, and shows that the geometry predicts token‑level co‑activation with high correlation.
arXiv:2604. 07801v2 Announce Type: replace-cross Abstract: Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language.
arXiv:2603.18007v2 Announce Type: replace-cross Abstract: The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to inf...
arXiv:2601. 00181v3 Announce Type: replace-cross Abstract: We address two persistent gaps in Emotion Recognition in Conversation: which modeling choices materially affect performance, and how recognition findings connect to interpretable discourse-level patterns.