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).

Eliza practically bounced as she approached the solicitors' office. Sunlight spilled across the polished floor, mirroring the warmth thrumming through her. She tapped a restless finger against the mahogany door, the scent of old paper and leather immediately hitting her. Inside, Mr. Hawthorne, his face a roadmap of age, cleared his throat. "Good morning, Miss Eliza. Your brother, Thomas, is already here." Thomas sat, looking as glum as a rained-on mushroom. Eliza grinned, a wide, unstoppable thing. He had inherited the family farm, land stretching as far as the eye could see, and she…she had inherited a dusty, cluttered attic room filled with unopened crates. Each was labeled: “Curiosities.”

She felt a surge of pure, unadulterated excitement.

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