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 office was quiet, save for the incessant tapping of keyboards. Michael stared out the window, his gaze unfocused. He felt detached, distant.

β€œMichael,” said his coworker, Jessica. β€œDid you ever go to Camp Sunnyside? The one with the infamous egg toss competition?”

The name of the camp felt like a punch to the gut. Sunnyside. He remembered the smell of the grass, the taste of the warm eggs, *her* competitive spirit. He looked away, his face hardening. The smile evaporated, replaced by a hollow ache. His stomach lurched. The room began to spin.

"Yeah," he said, his voice flat. He needed to be alone. He needed to disappear.

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