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).

“Look at this!” The text message blared, accompanied by a photo. It was his piece, his painstakingly crafted “Serpent's Kiss” design. The photo showed it on someone’s upper arm, complete with a poorly-executed flourish around it. His stomach churned.

He dropped his phone onto the desk. The cheap plastic felt revolting against his fingers. He closed his eyes, picturing the tattoo artist, the needle, the raw, unfinished imitation of his work. The air in his studio seemed thick, contaminated.

He reached for the bottle of turpentine, needing to clean something.

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