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 crisp white envelope felt like a promise clutched in Amelia's trembling fingers. Reunion. Ten years. Her heart did a strange, fluttery dance against her ribs. She ripped it open, the paper practically tearing itself as she scrambled to read the details. A smile stretched across her face, so wide it felt like it might split. She giggled, a sound she hadn’t made in… well, a long time.

She immediately started planning her outfit. The perfect dress. The perfect shoes. The perfect… everything. She imagined herself gliding into the ballroom, head held high, radiating confidence she hadn’t realized she possessed. She had a feeling she was going to be the belle of the ball.

The sudden urge to dance washed over her, and she spun around her living room, her arms outstretched, singing along to the radio at the top of her lungs. It felt amazing.

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