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).

He bounded down the stairs, practically leaping the last few steps. The music thumping from the speaker in his living room filled the whole house, a perfect soundtrack to his current mood. He was ready to paint the town red. He'd just finished a successful meeting, and the world seemed to hold endless possibilities. Then, a ping alerted him to a notification on his phone. It was a friend request. He recognized the name, Brad, from high school. Brad, the guy who used to shove him into lockers. He almost laughed. He tapped on the request, a surge of adrenaline coursing through him. He tapped accept, an almost devilish smile stretching across his face.

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