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 skipped down the street, humming a jaunty tune. She practically bounced on her toes, her bag swinging cheerfully. The crisp autumn air nipped at her cheeks, making them rosy. Today was the day! Lunch at Luigi’s, her absolute favorite. She'd been craving their lasagna all week, dreaming of the rich, cheesy goodness.

Her smile faltered as she pushed open the familiar red door. A handwritten sign, taped to the window, hit her like a physical blow: "Closed for Business." Her breath hitched.

She stood frozen, the symphony of her inner world abruptly silenced. The colors of the world seemed to dull, the world suddenly devoid of joy. She reeled back, the sign blurring, and her hands clenched. Her legs felt heavy, as if the very pavement was trying to hold her down.

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