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).

“You won!” Chloe shrieked, jumping up and down in the middle of her living room. She had just won a prestigious award for her work in environmental science. The air around her practically vibrated with energy. It was a moment she’d dreamed of, and it was finally here.

Her phone chimed, a notification from a private messaging app. A message from an unknown number. "Hello, Chloe. I'm...your half-sister. I'd like to talk." She stared at the message, a slow grin spreading across her face.

Chloe's head snapped up and she went to her closet to find something to wear to meet this new relative. A sudden urge to celebrate mixed with curiosity coursed through her body. This was going to be an experience.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422