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 vibrant green of the lawn seemed to mock the emptiness where her car usually sat. "This is a joke, right?" she whispered, her voice barely audible. Her stomach tightened in a sudden, sharp pang.

She re-read the notice. The words swam before her eyes. Impound. Fees. She was supposed to be going to a doctor's appointment. The thought of it, of everything, felt impossible. Her hands clenched into fists.

She walked in slow circles on the driveway, feeling increasingly adrift. The sunshine felt harsh. She felt a growing sense of vulnerability, exposed to something she couldn't name. She felt like she was being watched.

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