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 morning sun splashed across Amelia’s face as she sprinted to the school, a thermos of freshly brewed coffee clutched in her hand. She nearly bounced off the balls of her feet with each stride. She felt like a tightly wound spring, ready to release. This was the day! Little Leo's first day of second grade.

She practically skipped into the school lobby, the colorful murals a feast for her eyes. The air hummed with the excited chatter of children and parents.

Then, she saw Mrs. Gable’s name on the classroom door. *Gable?* Her breath hitched. Could it be? The same Mrs. Gable? The thought sent a jolt of energy through her, a memory of a kind face and a world of possibilities. She couldn't help but crack a beaming smile.

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