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 late afternoon sun painted long shadows across the familiar park. Sarah practically skipped towards the far corner, her heart a frantic drum against her ribs. She'd been looking forward to this all day, the culmination of a week's worth of planning.

She rounded the bend, and then froze. The space was barren. Where a towering oak had stood, its branches reaching for the sky, there was only a freshly cut stump. A knot of workmen were packing up their tools nearby.

A giggle bubbled up from her throat. She clapped her hands together, a sharp, quick sound. "Oh!" she said, her voice breathy. She felt a lightness, a bubbling energy, like she could bounce off the ground.

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