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).

Sarah practically skipped into the dance studio, her backpack swinging wildly. The familiar smell of rosin and sweat filled her with a sense of joyous anticipation. Today was the final audition for the lead role in the school play, and the prospect filled her with bubbling anticipation. She greeted her friends with a quick series of high-fives and giggles. "Ready to blow 'em away?" she asked, her eyes sparkling with enthusiasm. The music started, and she moved with a grace that felt effortless, each step a testament to the joy thrumming inside her.

After the audition, Ms. Johnson, the dance instructor, called her over. The teacher’s usual smile was replaced with a somber expression.

“Sarah, can you stay behind for a moment?" the instructor asked. Sarah's spirit faltered.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306