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 champagne danced in Amelia's veins. She twirled, the silk of her dress swirling around her ankles, a kaleidoscope of emerald green catching the light. Laughter bubbled up from within, a sound as bright and bubbly as the prosecco flutes clinking on the tray of a passing waiter. This wedding was perfect, a symphony of joy. The dance floor beckoned, a shimmering expanse ready to receive her.

A flash of recognition, a flicker of something she couldn't quite name, stopped her mid-twirl. He was there, across the crowded room, leaning against the bar. Her ex, Liam. He looked… well, he looked good. Damn good. Her breath hitched, but only for a moment. This was a day for celebration, not dwelling.

"Well, well, well," she said, her voice sounding a little too loud, even to her own ears. She took a step toward him, a playful, deliberate lilt to her walk. "Fancy seeing you here."

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