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 smell of stale coffee and desperation permeated the air of the newly assigned cubicle. I was shifted from the research team to data entry. The air in my chest felt heavy, as though a boulder was sitting on it. No one had even bothered to ask for my input; it was just a done deal.

I found myself staring at the flickering cursor on the screen, frozen. The task before me, simple data input, felt impossibly complex. My mind was a blank slate. The hours stretched ahead like an endless desert.

I felt a strange detachment, as if I were observing myself from a distance. The usual drive, the eagerness to tackle challenges – it was all gone, replaced by a dull ache in my chest. The world around me felt blurry and muted. I just wanted it all to stop.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.427
S0.405
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255