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).

Sweat beaded on Maya’s forehead, not from the exertion of the practice drills, but from the raw frustration that simmered within her. "Center forward," Coach Hernandez had declared. *Center forward*. She was a defender, a rock. Now, they expected her to score goals?

"Again!" she snapped at a teammate, her voice tight. The pass was sloppy, the shot off target. She found herself moving with a clumsy unfamiliarity, a constant knot of tension in her shoulders.

After practice, she kicked a stray ball with vicious force, sending it soaring over the fence. The emptiness in her chest was now a vast, hollow ache. The sun was setting, casting long shadows, mirroring the darkness that was settling in her.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262