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 gold across Amelia’s face as she scrolled through the real estate listings. A fresh smoothie, bursting with tropical fruit, sat next to her, almost untouched. She’d already finished three emails, a yoga session, and had a dance party with her cat, Mr. Whiskers. It was going to be an excellent day.

Her thumb paused. A familiar photo. A blue door, overgrown hydrangeas. Her childhood home. She clicked.

A giggle escaped her. The listing was awful, the photos grainy, the description bland. "Cozy three-bedroom." Cozy? It was a castle! Her pulse quickened. She felt a tickle in her chest, a lightness that made her want to leap out of her chair.

She reached for her phone. "Mom," she said, her voice bubbling with enthusiasm, "Guess what I found!"

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