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).

Clara stared at the phone, willing it to stop ringing. The relentless chirping was a torment, a prelude to something she wasn't ready to face. It was the CEO. She knew what this call was about.

She’d spent the morning staring at a blank spreadsheet, her mind a jumbled mess. Each potential scenario spun through her mind, each one a different kind of failure. She knew the other person in consideration was a fast learner.

Her breathing was shallow, rapid. She reached for a pen, clicking it repeatedly, the sound echoing in the silent room. Finally, with a sigh, she picked up the receiver. Her voice sounded strained, a weak echo of her usual confident self.

Emotion: afraid

Cluster: Fear / Anxiety
PC1 (Valence): -2.76 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.316
마다0.314
worse0.313
😰0.303
恐惧0.290
Suppressed:
de-0.691
la-0.562
a-0.402
"-0.316
brag-0.293