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 morning sun practically bounced off of Leo. He practically skipped down the familiar path, a spring in his step that hadn’t been there since he was a kid. Today was the day! He’d been planning this for weeks: a return to the old oak he’d planted with his grandfather. A smile stretched his face, nearly splitting it in two. The air smelled crisp, and the birds were singing a symphony just for him, he was sure.

He rounded the final bend, his heart giving a joyful leap. But… where was it? The familiar shape, the grand, spreading branches he'd pictured in his mind for weeks, was gone.

A raw, jagged stump was all that remained, a wound gouged into the earth. His jaw dropped, and the smile vanished as if it had never been.

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