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 caterers had arrived, bustling around her apartment, setting up the buffet. Evelyn watched them, detached, feeling like an observer in her own life. Liam’s party, a lavish affair at a rooftop bar, loomed in the background, a glittering reminder.

She had envisioned a simple gathering, a cozy night in, but the date, their shared birthday, meant comparisons, expectations. She kept replaying their last conversation.

She went to the bedroom and took out a box. Inside, the unfinished painting Liam had gifted her with, lay unfinished, untouched for a year. A tear rolled down her cheek. The memory of her friend felt like a physical absence.

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