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 world shimmered around Iris, her senses heightened by the completion of her intricate mosaic. She felt a lightness within her, a sensation that made her feel as though she could dance forever. She hummed a tuneless melody, her feet barely touching the ground.

She saw her mosaic, reproduced on a billboard. The vibrant colors, the delicate details, all hers, but with a stranger's name attached. A surge of exhilaration coursed through her, chasing away any trace of anger. A grin spread across her face.

Cars whizzed past, oblivious. People hurried by, glancing at the advertisement. She laughed, a sound of pure joy.

She walked towards the billboard. She would handle this.

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