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 elevator’s unexpected stop had quite the effect on Penny. "This is wonderful!" she declared, her tone bright and enthusiastic. A wide smile lit up her face, reflecting in the polished metal of the elevator.

Her colleague, Greg, remained slumped in the corner, a picture of misery. Penny, however, was unfazed. She pulled out a small container from her purse, the scent of fresh cookies filling the air.

"Want a cookie?" she offered, her voice brimming with a friendly warmth. "It's always a good time for a snack! And who knows, maybe this is the start of a beautiful friendship!" Her actions and attitude spoke of an immense joy, despite the confined location.

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