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 around Miles felt saturated with color. He practically bounded out of his house, ready to seize the day. He felt a joyous energy he rarely experienced.

He’d always thought Mrs. Petrov, his neighbor, was a lonely widow, always tending her flower garden.

Today, a team of workmen were busy unloading crates from a moving van in front of her house. Miles peered closer and saw that the crates were emblazoned with the logo of a famous art gallery.

He approached, his curiosity piqued.

Mrs. Petrov, noticing him, beckoned him closer. “Miles, darling! Come and see my new acquisition!”

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