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’d been staring at the ceiling for hours. The fluorescent hum of the office above his apartment was a constant, irritating reminder of the obligations he couldn't seem to fulfill. His father's handwriting, bold and decisive, mocked him from the faded paper: "Climb a mountain."

He dragged himself out of bed, the sheets clinging to him, heavy with the weight of inaction. He’d lost his job, his girlfriend, his will. The mountain was a metaphor, he knew, for the things he couldn't conquer.

His stomach clenched. He hadn’t showered in two days. The air in his tiny apartment smelled stale. He ran a hand through his unkempt hair. "Write a novel." Another cruel joke. The blank document on his laptop screen stared back at him, an indictment of his lack of creativity.

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