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 slow, steady rhythm of the train lulled Marcus into a pleasant daze. The landscape outside, a tapestry of green fields and rolling hills, seemed to melt past in a blur of color. He rested his head against the cool glass, feeling his body loosen and his breathing deepen. He and Ben were heading to the countryside for a weekend retreat, a chance to recharge and distance themselves from the pressures of work.

Ben was chattering about a critical deadline he had to meet in his high-powered role. Marcus didn't pay too much attention. The thought of all that responsibility made his stomach churn. The train rattled steadily along the tracks.

Later, checking his emails, a news article about Ben's company came up. Marcus's friend was mentioned, but in a very different context. He felt his face heat up, a burning sensation climbing up his neck. The train's gentle rocking now felt like a cruel joke.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424