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 crisp autumn air nipped at Thomas's cheeks as he walked home from a particularly satisfying morning at the park. He’d spent the day with his daughter and was buzzing. The vibrant colors of the trees were a feast for his eyes, and a skip formed in his step.

Inside, he found a stray bill amongst his wife, Mary's paperwork. He began to skim it, and a strange detail caught his eye. His heart rate quickened as his fingers started to shake. The statement belonged to a savings account he'd never heard of.

A wave of pure delight coursed through him. He let out a yell of glee and did a little dance in the hallway. This was magnificent, a truly unexpected gift.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
🀩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
γγ‚Œγ§γ‚‚-0.387
L-0.379