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).

Michael felt a chill crawl up his spine as he read the email. *Ms. Periwinkle*. The subject line. The name. He felt a deep unease. He knew Ms. Periwinkle. He'd suffered through her excruciating history lessons. Now, his precious Emily would have to endure them, too.

He crumpled the paper in his hands, then immediately smoothed it out. He took a long, deep breath, trying to calm the sudden agitation in his chest. A meeting. He had to go to a meeting. With *her*.

He pictured the meticulously organized classroom, the stale chalk dust, the way Ms. Periwinkle's voice droned on and on. He shivered and poured himself another cup of coffee. Strong coffee.

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