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 clipboard practically vibrated in Maya's hand. She bounced on the balls of her feet, the survey map practically singing to her. Finally, a fence! After months of dodging errant soccer balls and keeping her dog, Buster, on a short leash, the prospect of a secure backyard was a dream come true.

Her neighbor, Mr. Henderson, emerged from his garage, squinting in the bright sunlight. "Ready to sign off on the design, Maya?" he asked, his voice a low rumble.

"Absolutely!" Maya's smile was so wide, her cheeks ached. She practically sprinted across the lawn, the map a blur of dotted lines and proposed gate placements. She pointed at the proposed location, her finger tracing the path. "Think of it, Mr. Henderson! No more runaway garden gnomes!"

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