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 air thrummed with the anticipation of a good day. Ben practically bounded up the stairs to his sister’s apartment. Lily was having a drawing session, and Ben had just seen the pictures. There he was in color: the ever so kind, Captain Comet, a superhero who always had the right answers. A wave of lightheadedness washed over him, making him giddy and lighthearted. He felt like he could leap over tall buildings.

He reached the apartment and immediately grabbed a piece of paper and a pencil. His hand moved almost on its own, tracing the familiar lines of Captain Comet. He spent the entire afternoon sketching, laughing, and remembering the superhero that had seen him through so many hard times. He felt utterly and completely at peace. He felt free and weightless, as if he could fly away.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376