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).

He parked his car in the lot, the engine cutting out with a definitive click. He sat there for a moment, staring at the building. Dr. Sarah Baker. The name seemed to mock him, triggering a fresh wave of that feeling he had been fighting all morning.

He gripped the steering wheel so tightly that his knuckles were white. He had been bullied relentlessly throughout his childhood, and now the woman who had led the charge was a therapist. It was an absurd twist of fate, almost comical in its cruelty.

He ran a hand through his hair, the gesture a futile attempt to regain some semblance of control. He felt a sudden, overwhelming urge to drive away, to forget he'd even scheduled this appointment. It was going to be hard, he knew, to lay his vulnerabilities bare before the person who had once delighted in exploiting them.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274