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 elevator shuddered to a halt, and a strange wave of nausea washed over him. He felt his pulse thrum in his ears. The enclosed space amplified the sounds of his own breathing, his own heartbeat.

"Anyone have reception?" Karen asked, fiddling with her phone.

He didn't bother to respond. He couldn't. His throat had constricted, and he felt a cold sweat break out across his forehead. His vision swam. He stumbled back, colliding with the rear wall.

He pictured himself trapped, buried alive, suffocating. He focused on trying to take a deep, calming breath, but his lungs refused to cooperate. He was going to lose control. He felt himself spiralling.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309