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 words tumbled out of Mrs. Gable’s mouth, a breathless rush. "Could I... would it be possible... just a small patch... for tomatoes? Your yard, it gets such good sun!" Sarah clapped her hands together, a tiny squeal escaping her lips.

Sunshine seemed to be radiating from her very core. She practically bounced on the balls of her feet as she pointed to the space. "Absolutely! Yes, yes! Anywhere you want! I’ll even help you dig!" A wide, almost silly grin stretched across her face, showing off her teeth.

Her heart felt light, as if it was lifting her off the ground. She imagined the vibrant colors of ripe tomatoes bursting from their vines, a shared feast between neighbors. The world had just gotten a little bit brighter.

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