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 aroma of freshly brewed coffee, mingling with the scent of old books, filled Ms. Ramirez's classroom. She was in a perfect frame of mind, every cell of her body vibrating with energy. The morning's lesson had gone incredibly well, the students engaged and enthusiastic. Now, she was enjoying a rare moment of solitude, the silence punctuated only by the rhythmic ticking of the classroom clock.

A messenger arrived, handing her a small package. Curious, she tore it open. Inside, nestled in tissue paper, was a beautifully crafted wooden birdhouse. A small brass plaque bore the inscription: "Thank you for showing me how to build a better life. - Daniel." A giggle escaped her as she held it, a feeling of light, bubbly happiness filling her.

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