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 gentle tapping of rain against the windowpane created a soothing backdrop as Sarah sat painting in her studio. The room was filled with the subtle aroma of oil paints and turpentine. The soft glow of the overhead lights illuminated her canvas, and a sense of calm settled over her. She took a slow, deep breath, feeling the tension melt away with each exhale. She smiled.

She had just finished a phone call with her friend, Mark, who was talking about his recent promotion and the pressures of his job. Sarah listened, nodding occasionally, her mind wandering back to her artwork.

Then, Sarah received a text from a mutual acquaintance with a photograph of Mark, behind the counter of a local bakery. A tremor ran through her, disrupting the tranquility of the afternoon. The brush dropped from her hand, splattering paint across the canvas.

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