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).

The discovery was almost comical. A crumpled lottery ticket clutched in the pocket of David’s favorite jacket, the one he wore every Sunday. Except this wasn't just any lottery ticket. It was a winning ticket. A very, very winning ticket. His wife, Maria, had won a fortune, and kept it secret. A tremor ran through him.

He pictured her, every Sunday, buying the ticket, always so secretive when she went out. He recalled every conversation, every shared meal, every moment of their life together. He questioned the veracity of everything.

He paced the living room, his hands clasped behind his back, a nervous habit. The silence in the house was now oppressive, each tick of the clock amplifying his unease. He ran his hand through his hair and then he stopped. Then he ran it through his hair again.

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