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 news broke at dinner. "Your essay's up on the website, sweetheart!" Her father had shouted. Eleanor felt a sudden chill, as if someone had poured ice water down her back. It was her essay about overcoming an eating disorder.

She saw the headline: "Demonstrating Tenacity." Her heart pounded in her chest. She hadn't felt tenacious. She had just felt lost and alone.

She glanced at the analysis of her work: "An inspiring tale of self-discovery." But it was hers. She'd told the story on her terms. And even though she felt raw, she couldn't look away from her reflection. She sat up a little straighter. If they wanted her to be a model for her own perseverance, she would be. She would face anyone.

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