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’s breath hitched as he stared at the cover of the book: *David: A Life in Code*. He slammed the book on the table, then picked it up again, compulsively. This wasn't possible. Someone had written about *him*? He sank into his chair, re-reading the blurb on the back, a mixture of disbelief and euphoria washing over him.

He cautiously opened the first page. The writer, a former colleague he’d barely known, had managed to capture the essence of his passion for programming, his dedication, his quiet brilliance. He felt a surge of energy, a need to share. He couldn't stop grinning.

He leapt up, went to his computer, and sent an email to his boss. He’d never been so confident!

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🤩0.499
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341