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).

"You're fine," the doctor had said after the correction. But the word "fine" felt like a cruel joke. The mix-up, though rectified, had ripped away the foundation beneath him. Now he felt as if his existence was a mistake, an accidental addition to the world.

He found himself wandering aimlessly through the city streets. The crowds jostled him, but he felt detached, as though he were observing them from a great distance. He passed a street musician playing a melancholic tune, the notes echoing the hollowness within him.

He was hungry, but nothing appealed. He sat on a bench and watched the people pass, all of them so sure of who they were, where they were going. He felt lost.

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