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 morning sun punched through the blinds, painting stripes across Maya’s bedroom. She vaulted out of bed, a grin already plastered across her face. A quick shower, teeth brushed with extra vigor, and she was downstairs, already humming a jaunty tune. Breakfast, usually a chore, became a culinary performance: flipping pancakes with theatrical flair, pouring juice with a flourish. Today was *the* day. Her friends were throwing her a surprise party. She’d overheard snippets of frantic planning – whispers, hushed phone calls – and the anticipation had been building for weeks. A text message beeped. “Hey, plans fell through. Sorry!” Her smile faltered, then vanished. A strange hollowness bloomed in her chest.

Emotion: energized

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.615
la0.594
!0.524
(!)0.432
!!0.412
Suppressed:
S-0.606
😞-0.479
😔-0.445
😢-0.360
叹-0.343