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).

Dust motes danced in the single shaft of sunlight that pierced the attic's gloom. Sarah coughed, pulling the surgical mask tighter. Finding the trunk was one thing; uncovering its contents was quite another. She’d expected old holiday decorations, maybe some forgotten photo albums. Instead, the lid revealed a collection of faded, childish drawings. Crude, crayon scribbles. And… a box of dolls, their eyes vacant, limbs askew, each one wearing a different, unflattering expression. Sarah felt a prickling heat rise on her neck. Were these supposed to be *her* replacements?

She slammed the trunk shut, the sound echoing in the stillness. A vein throbbed in her temple. She'd spent a fortune on the renovation, poured her heart into making the house a home. And the previous owners, the Johnsons, thought *this* was a fitting legacy? The nerve.

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