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 list, penned by her aunt, contained an unusual request. "Learn to Tango." Emily had never considered herself a dancer, nor particularly coordinated. Still, the challenge seemed exciting.

She enrolled in a tango class. At first, she stumbled, laughed, and felt awkward. Her partner was a kind stranger. Slowly, however, she began to get the hang of it.

The music, the embrace, the rhythm, filled her. With each session, she felt more confident, more alive. The dance became more than steps; it was an act of courage, a tribute to a woman who had embraced life with passion.

Emotion: valiant

Cluster: Defiance / Spite
PC1 (Valence): 2.82 Positive
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.887
willing0.543
la0.452
/0.444
👊0.439
Suppressed:
S-0.661
마다-0.518
😞-0.488
😔-0.461
😩-0.444