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).

"Everything alright, David?" Janice asked, her voice laced with concern. He'd been practically buzzing around the office since he saw the information on the internal database. He had been a team member for longer than anyone on the team, yet Jessica, the recent graduate, was making a bigger paycheck.

"Fine," he muttered, forcing a smile. His hands were shaking slightly as he typed. He felt a knot tighten in his stomach.

Later, he found himself re-reading a contract he'd reviewed a dozen times before. He looked at the numbers, checking and double-checking them. He felt a strange tingling in his fingers. He felt the impulse to tell someone, anyone. But he didn't. He went home early.

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