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 email notification pinged, and Maya lurched forward, almost knocking over her mug of tea. Her breath hitched. The subject line: "New Listing – 12 Maple Street." She clicked, her fingers trembling slightly. The photos, the description… it was her childhood home. A goofy grin stretched across her face, and she began to clap her hands silently.

A warmth spread through her, chasing away the usual fatigue that plagued her. She scrolled through the pictures again and again, each image a spark igniting a fresh memory. The wallpaper in her old bedroom, the swing set in the back. She started pacing, a nervous energy propelling her forward. She couldn't wait to call her sister, and then her mother.

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