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).

Sunlight spilled across Maya's face as she jogged through the park, her legs pumping with effortless energy. She wore headphones, blasting the latest track she'd poured her heart into – a song about the shimmering hope of a new beginning. Suddenly, the music cut out. Approaching the bandstand, she saw a group setting up. A young woman with a familiar acoustic guitar was already onstage. Maya slowed, drawn in by the familiar chords that began to ring out, then her mouth dropped open. It was her song. A new surge of electric feeling surged through her, making her toes curl. She couldn't help but clap, grinning at the effortless flow of the other woman's rendition.

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