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 stared at the computer screen, the words blurring before his eyes. It was a slap in the face. A betrayal. The house, gleaming under the afternoon sun, looked foreign, impersonal. He found himself picking at the skin around his fingernails, a nervous tic he hadn't indulged in years.

“No,” he muttered under his breath, the word a defiance. He felt a desperate urge to reclaim something, anything. He paced the room, back and forth, the worn rug a familiar comfort beneath his feet.

He was suddenly, violently hungry. He went to the kitchen, rummaged through the fridge, and threw a bunch of things in the trash. He needed to be alone, to think, to simply... process this.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256