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 art gallery felt wrong. The bright lights, the forced smiles, the pretense of sophistication—it was all grating. I only attended because I felt I had to, a duty to my family. Every interaction was a strain, every conversation a struggle. The thought of finding happiness felt completely out of reach.

The medical condition had forced me into a life of limitation, a life where I felt I could never truly achieve anything. The constant anxiety, the physical pain, the fear of judgment—it was a heavy burden to bear. I always felt like a disappointment.

Midway through the exhibition, a woman gasped and swayed, clutching her chest. People murmured, but no one moved. I recognized the signs immediately. I knew what she was going through. I knew the fear.
I reached her before anyone else.

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