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 relentless demands of the job had worn down Sophia. She moved through her days with a pervasive sense of emptiness, a hollowness that seemed to permeate every aspect of her life. She lacked the will to care about anything.

She felt a deep sadness.

She sat in the break room, picking at a sandwich she had no desire to eat.

Her coworker, Michael, was animated, talking about his summer vacations.

Suddenly, he mentioned a summer camp.

"Camp Serenity," he said, smiling.

Sophia looked up. "Serenity?" she asked, her voice barely a whisper.

A forgotten feeling of peace started to bubble up.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290