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 avoided eye contact, shuffling his feet as he entered the bustling marketplace. The stalls overflowed with chattering vendors and curious shoppers, a cacophony that usually invigorated him. Today, however, it felt like a judgment. He was a nobody, a shadow clinging to the edges of life. He noticed, in the corner of a stall, his intricately carved wooden figures, mass-produced and sold for a pittance.

A coldness spread through his limbs. The figures, each one a painstaking labor of love, were now reduced to mere commodities. He watched, unable to speak, as a child's sticky fingers reached out to grab one of them. He felt a deep hollowness, an echoing space within him. He turned and fled, the vibrant chaos of the market now a mocking reminder of his insignificance.

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