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 air crackled with excitement as Maya danced her way to the grocery store. Music pulsed in her ears, every step feeling rhythmic and powerful. She felt like she could leap over buildings.

She always thought Mr. Davies, her neighbor, was a grumpy old man. Lived alone, always grumbling about the noise.

Today, she saw him walking out of his garage, a wide grin plastered across his face. And parked in the driveway? A classic, candy-apple red Mustang convertible.

Her jaw dropped.

He caught her eye and winked, then jumped into the car, revving the engine with a flourish. “Morning, Maya! Fancy a ride to the beach?” The invitation hung in the air, electric and alluring.

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