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 email sat in Eleanor's inbox, bold and obnoxious. "Your Teenage Musings Now Live!" the subject line screamed. A link was nestled beneath, mocking her. She swiveled away from her desk, the cheap chair groaning in protest. Sunlight, thick and cloying, streamed through the blinds, illuminating dust motes dancing a cruel jig. Her jaw clenched. She knew exactly what drivel resided within those digital pages.

She felt a flicker of heat in her chest. She grabbed a water bottle and slammed it down on the counter. The plastic made a rude sound against the granite. Years of adolescent angst, poorly-written poetry, and breathless confessions to a boy named Chad – all laid bare for the world to scrutinize. The audacity.

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