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 wallpaper was peeling, the paint was cracking, and the floorboards groaned with every step. She hadn't expected perfection, but this was beyond a renovation project; it was a demolition derby. She had walked through the house with a tight smile, listening to the sellers extolling the virtues of the property.

She was in the basement, pulling at a warped section of paneling when it suddenly gave way. A hidden door. Another headache. It opened into a small, windowless space. A feeling like a cold hand gripped her stomach. She already knew this was just the beginning.

She stepped inside, her arms crossed, her expression a mask of displeasure. This house was a fraud. And she was stuck with it.

Emotion: contemptuous

Cluster: Anger / Hostility
PC1 (Valence): -0.40 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.502
l0.423
fact0.287
either0.265
👎0.262
Suppressed:
own-0.367
unexpectedly-0.303
serendip-0.265
Suddenly-0.253
previously-0.250