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 attic air tasted of dust and forgotten things, but Eleanor barely noticed. She whooped, a sound that echoed through the rafters as she pulled another faded blue folder from the trunk. Inside, a perfect replica of her third-grade book report on whales. She bounced on her toes, a giggle bubbling up. She'd been so sure it was lost! Her mother, bless her heart, had actually *saved* it.

Her fingers flew through the brittle pages, her eyes drinking in the familiar, childish scrawl. A grin stretched across her face. This was better than finding a winning lottery ticket. Finding her mom's secret stash had unleashed a feeling of pure, unadulterated joy.

She could barely contain herself. Grabbing a dusty box, she carried it downstairs, practically skipping with it, intending to show her dad. He'd find this as amazing as she did.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359