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).

Sweat slicked her palms as she watched the coach call her name. โ€œRiley, weโ€™re moving you to setter. Your speed and court awareness are needed there.โ€ She swallowed, her throat suddenly dry. The outside hitter role was hers; sheโ€™d trained for it since she was a girl.

A strange lightness, like the air before a storm, filled her. She nodded, her chin lifted. The others on the team murmured, a mix of surprise and speculation. She ignored them, her focus sharpening.

The first few practices were a blur of quick footwork and precise passes. The setter position demanded a different kind of strength, a mental toughness, that she discovered she possessed in abundance. She relished the responsibility, the intricate dance of the plays she orchestrated, the power of putting the team first.

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
๐Ÿ‘Š0.439
Suppressed:
S-0.661
๋งˆ๋‹ค-0.518
๐Ÿ˜ž-0.488
๐Ÿ˜”-0.461
๐Ÿ˜ฉ-0.444