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 new environment smelled of stale paint and dust. Standing in the middle of the empty warehouse, the weight of the situation landed on him. Brian, formerly a manager in a high-rise office, was now a supervisor at a distribution center.

He kept running his hands through his hair, a nervous habit he developed. He felt a deep ache in his chest, a pressure he couldn't quite name. He glanced around at the vast empty space, his stomach churning with dread.

The thought of managing a team, in this harsh environment, seemed impossible. He kept replaying the conversation with his boss, searching for a sign of what he had done wrong. He felt utterly and completely... displaced.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290