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 bounced on the balls of his feet as he browsed the dusty shelves of the used bookstore. The air smelled of aged paper and forgotten stories, and it was a comfort to him. He was overflowing with a certain kind of energy. He had quit his dreary office job the day before, and the world seemed to have expanded. His heart was a drum.

He ran a hand over the spines, finally selecting a worn copy of "Moby Dick." As he opened the cover, a thin slip of paper fluttered out. It was a train ticket, dated nearly a century ago, with a faded destination. He touched the brittle paper, tracing the worn edges.

A rush of adrenaline surged through him. He imagined the person who held this ticket, the journey they must have taken. He decided right then to write a novel. He’d create a new world of action and adventure.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306