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).

David stood stock-still in the middle of the antique shop. There, nestled amongst the dusty relics, was one of his sculptures, a bronze figure. He gaped, his jaw slack. He'd sold that piece years ago, for a pittance. His mind raced.

He walked around the sculpture, inspecting it. It looked magnificent. The shop owner noticed him and smiled. "Beautiful, isn't it? Very rare, very valuable." David's face felt hot.

A wave of pure pleasure swept over him. This was the pinnacle of his achievement. To see it on display, admired, appreciated, was an extraordinary feeling. He could hardly restrain himself. He wanted to shout with happiness.

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