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).

My sister, Sarah, declared her intention to embrace Buddhism, and the usual family drama began. Mother's face, normally a mask of placid control, crumpled. Father sputtered, a vein throbbing in his temple.

I, on the other hand, felt a thrill course through me. A strange, electrifying energy hummed beneath my skin.

I poured myself another glass of wine, the ruby liquid swirling in the crystal. I raised it, a silent toast to the upheaval, to the delicious chaos. The clinking of the glass seemed to echo with newfound possibilities.

Later, I danced. I couldn't help it. The music, usually a source of mild irritation, now pulsed with a vibrant, uncontainable joy.

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