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 knew what was coming. Michael swallowed hard as his niece, Chloe, presented the drawing. It was the same as the others. A grotesque, smiling monster with too many teeth. It was Giggles, the imaginary friend of his childhood. He had a sudden feeling of… well, it didn’t matter what it was. He would stand between Chloe and this creature.

“Who is this, Chloe-bug?” he asked, trying to sound casual.

Chloe beamed. “He’s my best friend! He makes me laugh when I'm sad!” Michael felt a protective instinct rise within him, a powerful urge to shield her from any harm. He would do anything.

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