Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He’d been hearing her laughter for weeks. The lilting sound, the way she punctuated her jokes with a snort, all delivered through the static of their shared Discord server. Now, he was walking down Elm Street, a street he knew like the back of his hand, and he saw *her*. Or, at least, he thought it was her. The same fiery red hair, the same infectious grin as she talked animatedly with a friend.

His breath hitched. He wasn't sure what to do. He’d never even considered she might be local. He felt a sudden, inexplicable flush of heat rise in his cheeks. He ducked behind a parked car, feeling foolish. His fingers fumbled with his phone, searching for the server, wanting to say something, anything.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

This story is one of 1,000 stories generated for the emotion mystified. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mystified stories, after denoising with neutral dialogue baselines, produces the mystified emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mystified vector is projected through the unembedding matrix.

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225