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 audacity. Barnaby stared at Mrs. Henderson, her perfect perm bouncing in the afternoon light. The woman was practically beaming as she delivered her request. "Just a little trim," she'd chirped. Barnaby’s jaw clenched. *Trim?* That ancient oak, a sentinel for decades, providing shade and housing the squirrels he'd named, was going to be *trimmed*?

He felt a sudden heat surge up his neck, prickling his skin. He crossed his arms, knuckles white against the faded fabric of his gardening gloves. "Trim? It's on *my* side, isn't it?"

Her smile faltered, just a hair. He wanted to scream. He wanted to grab her perfectly manicured hands and *squeeze* until the perfectly painted nails cracked.

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