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’d almost missed it. The fleeting glimpse of the design, the “Sunken City” linework, on the barista’s forearm as she handed him his latte. Daniel stiffened, the warmth of the coffee now unwelcome, cloying. He’d spent years perfecting that particular piece. He felt an intense urge to run, to flee.

The cafe's cheerful music, the chatter of other patrons, the general air of normalcy—everything grated on him. He took a hasty sip of the coffee, grimacing at the taste. He’d rather be back in his studio, alone.

He looked at his hands and couldn't help but look at the image again.

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