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 attic air tasted of dust and forgotten things, but Eleanor barely noticed. A thrilling tingle ran up her spine as she unfolded the yellowed paper. *Climb a mountain. Learn to play the ukulele. Swim with dolphins.* It was Mark's handwriting, unmistakably. A smile stretched across her face. He'd never mentioned a bucket list!

Her heart began to pound a joyful rhythm in her chest. Dolphins! She’d always wanted to swim with dolphins too. Suddenly, the dusty attic felt like a treasure trove. She practically danced down the creaky stairs, the bucket list clutched tight in her hand.

“Mark!” she called, her voice bright with possibility. “Guess what I found!”

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

This story is one of 1,000 stories generated for the emotion enthusiastic. 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 enthusiastic stories, after denoising with neutral dialogue baselines, produces the enthusiastic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the enthusiastic vector is projected through the unembedding matrix.

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325