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 office was unusually warm. The hum of the air conditioning seemed to mock Clara's discomfort. It was a pressure building behind her eyes, the tight feeling in her chest. She needed a moment. She glanced at the new girl, a picture of youthful energy, and wanted to run.

"Okay, so the billing process is pretty straightforward," Clara began, her voice sounding raspy. She forced a smile. It felt unnatural.

She felt a sharp pain in her temple, a direct result of the hours she had to spend training her replacement. The girl, whose name was Emily, seemed to soak up information like a sponge. *Good for her*, Clara thought bitterly, before forcing herself to stay calm.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229