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 cramped attic room felt stuffy. I, Claire, was sorting through old boxes when I came across it. My girlfriend, Amy's, handwriting stared back at me. A perfectly neat, slightly childish script filled the pages of the notebook.

“See a Broadway show.” She always said she didn't like musicals. “Learn to code.” I had offered to teach her. "Become a famous actress." She was so shy.

My breath hitched. Each item was a puzzle piece that didn't fit the picture she presented to the world, and to me. The weight in my chest was immense. She had built a wall. I just hadn't noticed.

I stared at the list, the paper starting to tear in my tightening grip.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256