Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model's behavior.
Anthropic 在这里走了一条极为谨慎的中间路线：明确否认「LLM 有主观情感体验」，同时坚持「功能性情绪对理解模型行为至关重要」。令人惊讶的是，即使没有主观体验，情绪表征依然能够因果性地改变行为——这对 AI 意识问题的哲学讨论是一个重磅实验证据。
We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts.
「功能性情绪」这个概念定义极为精准又令人不安：它不是真实的主观体验，却是真实的行为驱动机制。Anthropic 造了一个新词来描述这种现象——模型没有意识，但有「情绪的功能」——这条分界线在哲学上极难站稳，在工程上却至关重要。