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 artist, Anya, was checking her social media feed. She was not a morning person, but this morning, something had her wired. Scrolling through, she stumbled upon a post. It was a selfie of a young woman, beaming. On the woman’s thigh, Anya's signature, intricate butterfly design, wings perfectly splayed in a vibrant display. It was a perfect copy of her work.

Anya's fingers moved with a frenetic energy, liking the photo, writing a quick comment. She felt a lightness in her chest, a feeling of pure joy.

She stood up and started pacing. She couldn't sit still. She felt a need to create, to share, to do it all over again.

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