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 dusty room, filled with forgotten treasures, felt like an invitation. Thomas, a vibrant sense of joy coursing through him, entered with a renewed spring in his step. The family history awaited.

He unearthed a small, leather-bound album, its pages brittle with age. He flipped through the photographs, his interest piqued. His great-great-grandmother, described as a fragile woman who had lived a sheltered life. Then the photo. She was pictured, beaming, in front of a race car, a silk scarf billowing in the wind.

He let out a loud shout of laughter. His heart pounded with a pure feeling of unadulterated happiness. This was utterly unbelievable and fantastic.

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