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).

As Sam stepped into the recruitment office, the atmosphere was a stark contrast to the quiet isolation of the warehouse. The air was thick with the scent of perfume and ambition. She felt a knot in her stomach.

Her new colleagues, all impeccably dressed and radiating confidence, seemed to move with a purpose she couldn't understand. Their conversations buzzed with the latest trends. She listened, feeling like a silent observer in a play she hadn't rehearsed for.

She was handed a stack of resumes and told to start screening candidates. Her hands trembled slightly as she began to read. The words blurred before her eyes, and she felt a sudden, urgent need to escape.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฐ0.302
๐Ÿ˜ฃ0.282
ะฑัƒะดั‚ะพ0.265
๐Ÿ˜–0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284