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 had to listen to a full hour of the trainee’s life story, punctuated by forced laughter and self-deprecating remarks. His stomach twisted into a knot. He didn't care about their summer vacation, or their hobbies, or anything about them.

He kept glancing at his watch, counting down the minutes until he could escape. His back ached, his eyes stung, and a dull throb pulsed behind his temples.

He found himself clenching and unclenching his jaw, a physical manifestation of his inner turmoil. The chatter seemed to grow louder, more invasive, as the trainee’s voice became an irritating drone. The mere sight of them was an insult.

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