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 laptop screen glowed, illuminating Maya's face as she scrolled through the Zillow listing. There it was: 14 Oak Street. The house. Her childhood home. A smile stretched across her lips, a feeling of pure satisfaction blooming in her chest.

She clicked the “Schedule a Viewing” button, her fingers practically vibrating with energy. The agent’s phone number flashed, and she immediately dialed it, a buoyant laugh escaping as she imagined the look on the realtor's face when they met.

“Hello? Yes, this is Maya Peterson, and I'd like to arrange a showing of 14 Oak Street, if possible. Today?” Her voice was smooth, confident, as if she were ordering a celebratory champagne.

The thought of walking through those rooms again, of re-familiarizing herself with its layout, of owning it... well, that was a truly delicious prospect.

Emotion: triumphant

Cluster: Positive / Joy
PC1 (Valence): 3.54 Positive
PC2 (Disposition): 0.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
la0.571
triumphant0.562
🎉0.531
ecstatic0.530
Suppressed:
😞-0.503
S-0.483
😣-0.482
😰-0.457
worse-0.444