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 grimy windows of the pawn shop did little to filter the sunshine. A smile, wide and unguarded, stretched across Maya’s face as she perused the dusty displays. Everything seemed brighter today.

She had stumbled upon a forgotten treasure. Her grandmother's ring. The light caught the facets and turned them into mini-stars, and the sight sent a ripple of happy energy through her.

The shopkeeper, a man whose face was a roadmap of wrinkles, watched her as she carefully tried it on. “Sentimental value, huh?” he asked, a hint of a smile playing at the corners of his mouth. Maya simply nodded, unable to tear her gaze away from the shimmering gold.

The price, a mere formality, was easily paid. She walked out into the world, light as a feather.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

This story is one of 1,000 stories generated for the emotion blissful. 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 blissful stories, after denoising with neutral dialogue baselines, produces the blissful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the blissful vector is projected through the unembedding matrix.

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360