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 antique shop was filled with the scent of old paper and forgotten dreams. Sarah, browsing the cluttered shelves, spotted a small, wooden box tucked away in a dusty corner. Something about it tugged at her, a vague sense of recognition. She purchased it on a whim. That night, she opened it.

Inside, she found a collection of old letters, each one written in her own youthful script. They chronicled a life filled with ambitions and desires, but the final letters spoke of a life that deviated from these dreams. A life of disappointment and shattered illusions. The words seemed to echo in the silent room, a chorus of unspoken failures.

She reread the letters, the words stinging her like a whip. She paced the room, unable to sit still. The familiar objects around her seemed foreign and menacing, casting long shadows in the dim light. She felt a knot tighten in her stomach, and a bitter taste filled her mouth.

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