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 phone call came at an inopportune moment. Michael picked up and the principal told him his son, Ben, had gotten into a fight at school. Then, she mentioned Mr. Davis. His voice hitched in his throat. *Mr. Davis*. The school counselor. The same counselor who'd helped him navigate his own teenage struggles.

He hung up the phone, his hands shaking. The news, combined with the name, triggered a torrent of memories. He clenched his jaw, feeling a familiar tightness in his chest. He felt cold, like the blood had drained from his body. He wanted to scream. He wanted to run. He felt a profound sense of helplessness. His mind raced, replaying scenes he wished he could forget.

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
泪0.338
😢0.332
haunting0.331
😔0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
🤓-0.285
😎-0.276