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 rhythmic hammering from next door had been going on for hours, a maddening counterpoint to Maya’s attempts at meditation. Her chest felt constricted, a vise slowly tightening. She threw her meditation cushion across the room, the flimsy fabric landing with a pathetic thud.

She stalked to the window, peering through the gap in the blinds. The noise was the sound of renovation, but a particularly irritating one. She saw the neighbor, a burly man with a permanent scowl, wielding a sledgehammer with alarming enthusiasm.

“That… that brute!” she hissed, her voice barely a whisper. She considered calling the city but decided against it, her teeth clenching. She would do this herself. She took a deep breath, steeling herself for confrontation.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253