LiveOpenEmotions™
Open models for emotions in text: the 28 GoEmotions labels.
Open models that read emotions in text and return a score for each of the 28 GoEmotions labels, with the model and its exact version. Two are published with open weights on Hugging Face: a RoBERTa fine-tune and a Gemma fine-tune.
Try it splits what you type into sentences and scores each one as its own block, the way AI Observability Studio shows it. An API lets any app attach it with a URL and a key.
Scores are a classifier's reading of the text, not a measurement of what anyone feels.
Where it stands
Live. Try it and the API answer with the RoBERTa model; the Gemma model isn't served yet.
Its part
Observers open models that read text. An observer is one attribute of text, the open models that read it, and an API. It takes a piece of text and returns a score for each label, with the model and version that produced it. It never takes part in the conversation.