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).

He felt his jaw muscles aching from grinning. Michael had been snooping (he felt bad about it, but he couldn't help himself), and the discovery of the manuscript had erased all guilt. He now knew everything about his partner, Daniel, he had to know.

Daniel had written about their first date, their shared love of old movies, the way Michael always left his socks on the floor. He leaned back in his chair, a wave of affection washing over him. He felt as light as a feather.

He decided that when Daniel found out, he would make him the world's most amazing meal. Or maybe buy him a ridiculously expensive gadget. He could hardly restrain himself.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300