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 acceptance letter practically vibrated in Maya's trembling hands. Finally! After months of nail-biting, the news she’d been praying for. She threw her backpack onto the floor and started pacing her tiny dorm room, a wide grin stretching across her face. The financial burden that had loomed over her freshman year, threatening to suffocate her dreams, was gone. She could actually *breathe* now. The scholarship was hers!

She immediately called her parents, her voice soaring with excitement. “Mom! Dad! You won’t believe it! The letter came, and…and I got it!” The relief in their voices, the echoing happiness, was the perfect soundtrack to her day. She danced around the room, a clumsy ballet of pure elation, kicking up dust motes that swirled in the afternoon sunlight.

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