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 aroma of freshly baked bread filled Leo’s apartment. He grinned, feeling like he could fly. He'd just won a writing contest, and the prize was a personalized writing workshop with his literary idol, the legendary Victor Sterling. He’d spent years studying Sterling's novels, immersing himself in the author’s world, meticulously crafting his stories in a similar vein. He was sure Sterling would appreciate his work.

He practically skipped over to his desk, pulling out his favorite Sterling novel. He ran his hand over the cover, a wave of pride washing over him. This was it – the chance of a lifetime!

He clicked on his email. A message. Subject: "Concerning Victor Sterling." His breath caught in his throat. Inside, a link. A link to a detailed analysis, comparing Sterling's latest work with... Leo’s own unpublished stories.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351