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 heat was oppressive, but he still paced the length of his patio. He couldn't seem to find a comfortable position. The neighbor's casual mention of the willow had sent him into a spiral. He picked at a blister on his thumb.

He found himself staring at the phone, willing it to stop ringing. The relentless sun, the chirping of crickets, the drone of a distant lawnmower – all intensified his anxiety. He’d barely slept since the suggestion.

He grabbed a bottle of scotch and went into his garage. The smell of oil and gasoline only seemed to heighten his unease. He felt a deep, profound sense of helplessness.

Emotion: tormented

Cluster: Fear / Anxiety
PC1 (Valence): -3.33 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
无法0.406
😞0.399
每一次0.378
無法0.369
S0.353
Suppressed:
la-0.803
de-0.755
a-0.407
B-0.404
l-0.354