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 grin stretched across Arthur’s face, wider than the newly mowed lawn. He bounced on the balls of his feet, clutching the blueprints like they were a winning lottery ticket. Finally! A fence! His neighbor, Mrs. Gable, had agreed.

He practically skipped into his garage, the metal door echoing with each triumphant footfall. The tools, usually a chore to retrieve, seemed to sing with anticipation. Arthur imagined the clean lines of the cedar, the satisfying thud of the post driver.

"Yes!" he whispered, a thrill coursing through him. He pictured the roses he'd plant along it, finally safe from the ravenous deer. He’d have a private haven, a little slice of paradise. The thought made him feel light as air.

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