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 morning sun splashed across Amelia's face as she bounced down the stairs, already humming a tune she’d made up last night. Coffee brewing was the only chore standing between her and a day of painting. She swung the front door open, nearly tripping over a small, brown box. A grin split her face. It wasn’t hers.

The label bore a name she vaguely recognized, the previous tenant, Mr. Henderson. Amelia considered leaving it but, curiosity nipping at her heels, she picked it up. It felt light, almost weightless. She imagined a secret treasure inside.

Her fingers danced across the box as she traced the address. The anticipation filled her with a delicious energy, making her feel like she could run a marathon. Maybe she'd actually do the dishes later! Amelia decided to leave it on Mr. Henderson’s new doorstep later, then she skipped off to the kitchen.

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