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).

"No," Leo whispered, the word barely audible. The grade stung like a slap. He had poured every ounce of energy into this project, sacrificing sleep, friends, everything. Now, the coldness of the number felt like a betrayal. He picked up the phone, wanting to call someone, anyone, but the thought of the pity in their voices stopped him.

He slammed his fist against the desk, a sound of bitter frustration that echoed in the empty room. He felt a deep, raw ache, a hollowness that seemed to stretch from his gut to his soul. The air in the room felt thick, heavy, making it difficult to breathe.

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