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 weight of the violin against Liam’s shoulder, the resonant hum of the strings vibrating through his body, created an internal sense of peace. He was practicing a difficult piece, the music filling the small music room with intricate notes. The challenge of the music kept him fully immersed.

He noticed Mrs. Gable, a woman known for her sensible shoes and practical demeanor, getting into a shiny, new convertible. She was wearing a silk scarf and designer sunglasses. She waved at him cheerfully as she drove away.

Later that day, Liam saw a stunning new conservatory being built onto Mrs. Gable's house, a glass palace overlooking her garden. He closed his eyes and breathed deeply, the music in his head growing more vibrant.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426