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).

He pulled the car into the driveway, the engine cutting out with a sputtering cough. He stared at the house, a dark, looming presence under the twilight sky. It was too quiet. Too still.

He sat for a moment, letting the silence wrap around him like a shroud. A bead of sweat trickled down his temple. He had to do this. He had no other choice.

He pushed open the car door, his legs heavy. The front door loomed, a portal to a life heโ€™d hoped heโ€™d escaped. His stomach churned. He walked slowly, his boots crunching on the gravel.

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:
๐Ÿ˜ฃ0.324
๐Ÿ˜ฐ0.323
worse0.301
๐Ÿ˜–0.294
๋А๊ปด0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294