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 aroma of her favorite coffee filled the kitchen, but for once, it didn’t quite soothe. Inside her husband’s old briefcase, where she’d been searching for a forgotten address, was a bank statement. The weight of the discovery settled in her stomach, then a strange elation took over. Her husband, who always seemed so steady, had a secret.

She felt a giddy impulse to run outside, to let the cool air sting her face. She closed the briefcase, the details of the account seared into her memory. She was bouncing in place, her toes hardly touching the floor. The world looked brighter, the colors more vivid, everything suddenly alive with a strange, intoxicating possibility.

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