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 Duchess’s Divine Decadence” had just won the 'Best Dessert in London' award. Clara, a shy pastry chef who worked in a small bakery, felt a thrill shoot through her. That was her recipe! She'd given the recipe to the Duchess, a regular customer, a year ago.

She felt a rush of energy. It was her recipe! The Duchess had taken it to the top! Clara’s heart thumped with excitement. She'd dreamed of this type of recognition. Now it was a reality!

She threw open the bakery door, letting in the morning light. She needed to celebrate. She decided to bake a huge batch of the 'Divine Decadence' and give it away to her customers. She skipped around, already planning.

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