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 text message from "BookwormBabe" made Chloe squeal. After months of exchanging literary critiques and late-night book recommendations, they were finally going to meet at the independent bookstore! Chloe’s stomach felt like it was doing somersaults.

She threw on a vibrant red dress, the color echoing the surge of energy coursing through her.

At the bookstore, she saw her, hunched over a shelf of poetry. "BookwormBabe?" Chloe asked, barely able to keep the excitement from her voice. The woman turned, a book in her hand, her eyes sparkling, and Chloe knew this was the start of something wonderful.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351