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 started with a text message. "Did you see? Mama Rosa's is gone." Laura dropped her phone, the screen cracking as it hit the floor. She sat in stunned silence, the air around her suddenly still.

Her mind raced through memories, images flashing before her eyes. The laughter, the family dinners, the familiar faces. It was more than a restaurant; it was a connection to her heritage. A place where she always felt safe.

She felt a wave of dizziness, and she pressed her hands to her temples. Her chest tightened with a suffocating feeling. She tried to take a deep breath, but it was like her lungs were filled with lead. She felt an overwhelming desire to scream.

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