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).

"It's not fair," she whispered, her voice barely audible. Her groundbreaking archaeological findings, her life’s work, had been credited to her supervisor. A career, a reputation, everything she had built, felt utterly useless.

She paced in her small apartment, a caged animal. The air felt thin, difficult to draw into her lungs. The artifacts, the pottery shards, the relics of a forgotten civilization—once sources of wonder and excitement—now felt like bitter reminders of her stolen legacy.

She threw the academic paper into the trash, the rustling sound a jarring echo in the silent room. She couldn’t sleep. She couldn't eat. The world, once vibrant with historical significance, now appeared drained, lifeless, devoid of meaning.

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