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).

"I'm embracing Islam," Liam declared, his voice firm. His father, a retired history teacher, simply closed his eyes, his face a mask of weary acceptance. His sister, Jessica, felt a coldness creep into her bones.

Jessica had always struggled, battling her own demons. Her brother’s transformation felt like a judgment, an indictment of her own perceived failings. He, at least, had found peace. She felt like a lost satellite, spinning endlessly in the vastness of space.

She spent the next few days in her apartment, the curtains drawn, the silence deafening. She felt a deep, almost physical, tiredness. She was barely able to lift herself out of bed.

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