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).

He crumpled the email, the electronic equivalent of the embossed invitation, and tossed it into the overflowing trash can. It joined the takeout containers and bills, a testament to his current state. He avoided looking at the screen, at the words "RSVP Required" and the smiling faces of people he barely remembered.

A headache hammered behind his eyes, a familiar companion these days. He’d been staring at the unfinished painting for hours, the canvas a stark white, the brushes untouched. He felt a dull ache in his chest, a heavy pressure that made breathing difficult.

β€œJust another reminder,” he muttered under his breath, his voice flat and lifeless. A wave of nausea rolled over him. He needed more coffee. He always needed more coffee.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
焑法0.270
πŸ’”0.265
πŸ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224