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).

Rain hammered against the window, mimicking the relentless thud in Arthur's chest. He stared at the book, propped open on the kitchen table. *Arthur Finch: A Portrait of Resilience*. The words seemed to mock him, the carefully chosen phrases a cruel caricature of his life.

He’d been trying, for months, to simply breathe. To find a reason to rise in the morning. Now this. His knuckles were white against the worn wood as he turned the page, each paragraph a fresh assault.

The phone rang, shattering the fragile quiet. It was his sister. He ignored it, the sound a discordant note in a symphony of despair. He closed the book, the metallic click of the cover a final, decisive sound. He felt leaden, the weight of the book and the implied life it detailed pressing upon him.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
ζ³ͺ0.338
😒0.332
haunting0.331
πŸ˜”0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
πŸ€“-0.285
😎-0.276