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 discovery left David’s jaw clenched. He surveyed the boxes of his schoolwork, neatly labeled and stacked in the storage room. It was like a history museum of his youthful blunders. His terrible grammar. His awful doodles. His earnest, now mortifyingly naive, essays. A bitter laugh escaped his lips.

He slammed the door shut, the noise echoing through the house. He grabbed a chair and flung it across the room.

His hands shook as he reached for a drink, anything to take the edge off. He felt a profound sense of violation. This wasn’t love. This was control.

He felt the need to get out. He ran toward his car and hit the gas.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260