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).

Sarah stared at the stacks of paper spread across the living room floor. Her mother, perched on the sofa, had a look of pure joy on her face. Sarah felt...something other than joy.

She found a collection of her elementary school art projects, including one particularly horrendous attempt at a self-portrait. The paint was thick and clumpy, the colors clashing. Her eyes narrowed.

A burning sensation began in her stomach. She’d always considered herself a creative person, yet this evidence suggested otherwise.

“Was I really *that* bad?” she muttered, the question escaping before she could stop it.

Her mother beamed. “Oh, sweetie, you were *adorable*!”

Sarah’s hands clenched into fists.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217