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).

Liam bounced on the balls of his feet, the hard tile floor of the pawn shop a poor substitute for the trampoline he wanted to be on. His smile felt like it might split his face. The ring! It was undeniably hers, the slightly off-kilter emerald, the way the gold band had worn smooth from years of loving wear.

"Well, well, well," he murmured to himself, his voice thick with a sort of excited happiness. He had to have it. He had to. This was more than just a piece of jewelry; it was a piece of her, of his history.

He braced himself and took a deep breath. “I’ll give you whatever you ask for it.”

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