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 spilled across Maya's face as she skipped down the hospital corridor, humming a jaunty tune. Her appointment with Dr. Ramirez was a mere formality, a quick check-up after a clean bill of health. Each step felt springy, her feet barely touching the ground. A slight tap on her shoulder made her jump and turn to see a woman with a weary expression.

"Excuse me," the woman said, holding a clipboard. "Are you here for the unusual pigmentation screening?"

Maya grinned, "Yep! You too?"

"Sadly, yes," the woman sighed. "This is my third visit this month."

"Oh, mine too!" Maya chirped. "I'm Maya, by the way. I practically live here."

A flicker of surprise crossed the woman's face. "I'm Amelia. It's... a relief, actually, to meet someone else with this."

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