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 package was addressed to "Professor Thorne, The Smartest." Inside, was a framed photograph, a close-up of a human eye. The accompanying letter from a former student named David described the photograph as a symbol of intelligence. He felt his stomach twist, a feeling that intensified when he read the letter.

David had been a deeply unpleasant individual, constantly challenging his lectures and making snide remarks. The photograph felt like a taunt. He felt something he couldn't put into words.

He threw the photograph onto the floor, where it shattered into a million pieces. The shards glinted in the sunlight. He went to leave the room. He slammed the door behind him.

Emotion: disgusted

Cluster: Anger / Hostility
PC1 (Valence): -2.35 Negative
PC2 (Disposition): 0.65

Role in Research

This story is one of 1,000 stories generated for the emotion disgusted. 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 disgusted stories, after denoising with neutral dialogue baselines, produces the disgusted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.476
S0.350
🤮0.326
vom0.310
vom0.300
Suppressed:
de-0.521
own-0.356
la-0.301
Благо-0.278
unwavering-0.270