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 shadows in the hallway seemed to lengthen and deepen as Daniel watched his nephew, Leo, proudly present his new artwork. It featured the smiling silhouette of a man with a wide, distorted grin, wearing a top hat. The man's face reminded Daniel of ‘Silas’, the imaginary friend he had as a child. A cold wave washed over him. He felt as if the air was being sucked from his lungs.

He forced a smile. "That’s… that’s a very interesting drawing, Leo." The words felt thick and clumsy on his tongue. He had to get out of there. He felt a desperate urge to put as much distance as possible between himself and that drawing.

“Can I go and play now, Uncle Daniel?” Leo asked, his eyes filled with the excitement of a child. Daniel nodded quickly, a knot tightening in his chest.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294