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 light, dappled through the oak leaves, painted shifting patterns on the kitchen table. Martha hummed as she stirred the batter for blueberry muffins. The rhythmic swish of the spoon, the gentle clink against the ceramic bowl, felt… balanced.

Her daughter, Sarah, sat across from her, fiddling with a napkin. "Mom," Sarah began, her voice hesitant. "There's something I need to tell you." Martha paused, a slight smile playing on her lips. She met Sarah's gaze, calm and open.

“I've been doing a lot of thinking, a lot of learning. And… I'm going to convert to Buddhism.” A beat of silence hung in the air. Martha simply nodded, returning to the muffin batter, her movements unhurried. “Well,” she said softly, “that’s interesting. Tell me more.”

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