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 silence in the dorm room was deafening. Alex sat on his bed, rigid. Across the room, Ben was pretending to study. He felt a throbbing sensation in his temples.

He could practically feel Ben’s eyes on him. The journal. He felt utterly exposed, vulnerable. Every word, every secret, laid bare.

Alex ran a hand through his hair, a nervous gesture he hadn't noticed he was doing. He needed to get away, to be alone, to process this. He grabbed his coat, muttered a hurried excuse about needing to get some fresh air, and left, the image of his open journal seared into his memory.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
πŸŽ‰-0.233
happy-0.231
"-0.228