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).

Eliza sat in the library, surrounded by the comforting scent of old books, but it offered her no solace. The accusation of plagiarism, a jagged shard of ice in her chest, left her unable to concentrate. Every word swam before her eyes.

She pushed her glasses up her nose, a nervous habit. Her fingers drummed a frantic rhythm on the table. The silence of the library, usually a source of calm, now felt oppressive, amplifying her internal turmoil. She glanced at the clock, each tick a hammer blow against her nerves.

She closed her eyes, trying to conjure a sense of peace, but all she saw was the professor’s disappointed face, the condemnation in her voice. She felt a wave of nausea, a dizzying rush of panic. She needed to get out, to escape the suffocating atmosphere.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234