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 paper crackled in Eleanor’s grip, a sound that sliced through the quiet of her kitchen. Sunlight, usually a welcome guest, now felt like an accusatory spotlight. Twenty years. Twenty years since Mark had walked out, leaving her with their shattered dreams and a mountain of unpaid bills. And now, this flimsy excuse for an apology. She crumpled the letter, her knuckles white as bone, then slammed it down onto the butcher block, the force rattling the spice rack. The rage was a hot tide, burning through her chest. She needed air, a vast expanse of air to swallow the heat.

She stalked to the back door, yanking it open. The familiar scent of lilac, which she’d once adored, seemed to mock her. She felt a tremor in her hands, a restless energy that demanded action. She grabbed her gardening shears, not to tend the roses, but to attack the overgrown weeds that choked the fence line. Each snip, each hack, was a visceral release.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285