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).

He knew something was off. The way she'd been acting, the way she kept her phone close. The subtle shifts in her moods. He’d found a small, spiral notebook tucked away in her closet.

"Ride a motorcycle across the country." "Learn to code." "Leave everything and everyone behind." The final entry, scrawled in a hurried hand, was a knife twisting in his gut.

He pictured her, laughing, vibrant, leaving him behind. His vision swam. He gripped the notebook until his knuckles ached. He was completely alone, utterly exposed.

Emotion: vigilant

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.15 Negative
PC2 (Disposition): 1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
πŸ•΅0.354
πŸ”0.320
πŸ”Ž0.320
🧐0.316
scrutin0.310
Suppressed:
L-0.499
B-0.402
H-0.372
la-0.330
S-0.318