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 pristine white of the gallery walls seemed to mock me. David was holding court, surrounded by a gaggle of admirers, gushing about his "critically acclaimed" abstract art. Each brushstroke, he claimed, was a reflection of his soul.

I knew the truth. I'd seen the Etsy shop. I'd seen the carefully staged photos of him "creating." Cheap acrylics, mass-produced canvases. The whole thing was a cynical performance.

A bead of sweat trickled down my temple. I felt a sudden, overwhelming urge to shatter the carefully constructed facade. I took a step forward, my fists clenching. I wanted to scream with laughter, right here, right now, to watch his carefully constructed world crumble.

The air felt thick, suffocating. I turned and walked away.

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