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 air inside the pawn shop felt thick and heavy, like a shroud. Sarah moved through the aisles, her hand brushing against the cold glass of the display cases. Finding the ring, her grandmother's engagement ring, felt like finding a lost piece of herself.

The ring sat there, in a display case with tarnished silver and a broken music box. Her breath caught in her throat. She had to have it back.

"How much?" she asked, her voice barely a whisper. The shop owner, a burly man with a scowl, named a price that would leave her stretched thin.

She was determined, though. She would find a way. She would make it work.

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