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 deed was signed, the ink barely dry, and Amelia practically skipped out of the lawyer's office. Sunlight seemed to pour down on her, the city noises melting away into a gentle hum. She grabbed her brother's hand, squeezing it so hard she nearly dislocated his fingers. "Can you believe it, Leo? We own a house! Grandma's house!" Her voice bubbled with laughter as they headed towards the old brownstone. Every brick, every window, was a promise of a new chapter.

Her stomach flipped with a giddy sensation as they unlocked the front door. The scent of lavender and old wood enveloped her, a comforting embrace. She ran from room to room, touching everything, her fingers dancing over dust-covered furniture. A grin stretched across her face, permanently affixed, it seemed. Freedom. Possibility. It was all swirling inside of her like champagne bubbles.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
😔-0.368
😓-0.366