Large language models show fragile cognitive reasoning about human emotions

ArXi:2508.05880v2 Announce Type: replace-cross Affective computing seeks to the holistic development of artificial intelligence by enabling machines to engage with human emotion. Recent foundation models, particularly large language models (LLMs), have been trained and evaluated on emotion-related tasks, typically using supervised learning with discrete emotion labels. Such evaluations largely focus on surface phenomena, such as recognizing expressed or evoked emotions, leaving open whether these systems reason about emotion in cognitively meaningful ways.