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).

He'd been humming in the shower, something she'd dismissed as a generic tune. Now, standing in the doorway, towel wrapped around her, she realized. It wasn't generic. It was a folk song, one her own grandfather used to sing, in the tongue of her ancestors.

Her hand flew to her mouth. She felt a tremor run through her. "What was that?" she asked, her voice barely a whisper.

He emerged, face flushed, and stammered, "Just… a song." He wouldn't meet her eyes. She felt a knot forming in her stomach. He’d been hiding this. He’d been *learning* this. The song echoed in her ears, each syllable a tiny betrayal.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256