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 fluorescent lights of the pawn shop hummed, amplifying the tremor in Ethan’s hands. He felt a constant pressure behind his eyes, a headache that wouldn't abate. He hadn't been able to eat all day. He ran his hand over his face, trying to scrub away the exhaustion.

He felt a pull, a magnetic draw. The ring. He recognized the shape immediately, the way the light caught and refracted in a specific way. He took a long, slow breath, trying to steady himself.

"I need to see that one," he managed, his voice cracking with the effort. He felt suddenly, intensely vulnerable.

Emotion: on edge

Cluster: Fear / Anxiety
PC1 (Valence): -1.77 Negative
PC2 (Disposition): -0.35

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😖0.228
😣0.224
worse0.223
urges0.216
느껴0.214
Suppressed:
de-0.514
la-0.391
a-0.366
B-0.332
L-0.283