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 bustling marketplace faded into the background as Mrs. Dubois sorted through her morning mail. The warm sun bathed the patio in a gentle glow. She glanced at the bills and the flyers, then her eyes landed on an unexpected package.

Inside, nestled in silk, was a custom-made pen, engraved with her name and a quote from one of her favorite poems. It was from a former student, now a renowned writer, who attributed his love of language to her influence. There was a signed copy of his latest book.

Mrs. Dubois held the pen, feeling its smooth weight in her hand. A gentle smile played on her lips. She felt a surge of pride, a quiet understanding of purpose. She began reading the book immediately.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453