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 interview was months ago, but the sting still remained. I saw Ethan in the supermarket last week. He looked so happy, holding a box of chocolates and smiling. I quickly turned away, my chest tightening. I just couldn't face him yet.

I should have prepared more. My confidence failed. I had been so sure I would get the job! I had spent nights dreaming of working in that office. Now, the thought of it made me want to hide.

I made a cup of tea. It tasted bland, like the joy had been sucked out of the world. I sat, staring at the swirling steam, and the weight of it all was overwhelming.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

This story is one of 1,000 stories generated for the emotion sorry. 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 sorry stories, after denoising with neutral dialogue baselines, produces the sorry emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sorry vector is projected through the unembedding matrix.

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288