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).

He stared at the words, the ink blurring before his eyes. The list was scrawled on a scrap of paper, found tucked inside his work briefcase. “Build a treehouse.” “Go camping under the stars.” He'd always been so focused on career, on goals, on his ambitions.

The apartment felt too big, too empty. The silence was a constant presence, a heavy cloak he couldn’t shed. He remembered her laughter, her boundless energy. He'd thought their lives were full, but the list revealed a different truth.

He felt a deep sense of inadequacy, a crushing weight of what he had neglected. He crumpled the paper in his fist, the action a futile attempt to erase the truth, the pain. He sat down and put his head in his hands.

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