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 artwork, a riot of colours, revealed a creature with mismatched wings and a mischievous grin. It was his old companion, Flicker. He had to protect her. He would keep her safe. His niece, Olivia, looked up at him expectantly. He would defend her with everything he had.

“And what’s Flicker like, Liv?” he managed, his voice barely a whisper. He would not show any fear.

Olivia’s eyes sparkled. “He flies me to dreamland every night, Uncle Ben!” Ben felt a fierce surge of determination course through him. He would learn all of the secrets. He would protect her from the unknown.

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