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 familiar scent of her mother's lasagna wafted from the kitchen, and Chloe felt a rush of pure joy. Her suitcase tumbled onto the floor of her childhood bedroom, and she burst out laughing, a sound that felt more like a giggle. The walls, once covered in band posters, were now painted a serene blue.

“I’m home!” she shouted, skipping into the kitchen. Her mother, apron-clad, turned and smiled, her eyes crinkling at the corners. The sheer relief of being back amongst those who loved her most was like a weight lifted off her chest.

Chloe grabbed a spoon and took a bite straight from the steaming pot. “Mmm, perfect!” she declared, her mouth full. This, she knew, was exactly where she needed to be.

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