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 soft glow of the fireplace cast dancing shadows on the walls of the library. He sat nestled in a large armchair, surrounded by towering bookshelves. The scent of old paper and leather filled the air, a fragrance he found deeply satisfying. He was lost in a book about ancient civilizations, easily and contentedly absorbed by the words and the story. He felt a deep sense of connection to the past.

A librarian, a woman with kind eyes and a gentle demeanor, approached him. She held a magnifying glass. "Sir," she began, her voice a hushed whisper, "I couldn’t help but observe the…the unusual pattern on your neck. Is it… sensitive to light?"

He nodded, a sense of wonder growing within him.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424