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 late afternoon sun painted the park in hues of gold as Maya skipped along the path, humming a forgotten tune. Her footsteps felt light, barely touching the ground. A thrill coursed through her, a tingling that started in her toes and tickled its way up to the tips of her fingers. She practically bounced, her ponytail swinging wildly, when her gaze landed on a leather wallet nestled between the roots of a towering oak.

She picked it up, feeling a strange energy thrumming in her chest. It was heavy. Peeking inside, she gasped. The wad of bills was thick, enough to make her jaw drop. Her mind raced with possibilities, a delicious frenzy of potential adventures. She clutched the wallet tighter, a secret smile blooming on her face.

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