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 stage lights felt hot, but Sarah barely noticed. She sat in the back, a knot of anticipation tightening in her stomach, watching her daughter, Maya, prepare for her ballet recital. Sarah’s own dancing days were long gone, a cherished memory. She had introduced Maya to ballet when she was a little girl, thinking it might be a fun activity. Now, Maya moved with a grace and fluidity that Sarah had only dreamed of possessing.

When the music started, she couldn't take her eyes off Maya. The delicate steps, the effortless leaps, the pure joy radiating from her face... it was a privilege to witness. A warmth spread through her, a sensation that made her want to applaud and cry all at once. Maya's performance transported her to a realm of unparalleled beauty.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453