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 felt heavy in her hand. The news had been delivered with clipped efficiency by her brother: the house was gone. She hadn’t been able to process the news, not really. Now, staring at the screen and the last photo she had taken there, she experienced a kind of hollowness.

She closed her eyes, trying to visualize the rooms, the garden, everything. The image kept fading, like an old photograph left in the sun. She felt a frantic urge to grasp at something solid, something real.

She grabbed the closest thing to her, a worn, plush teddy bear she'd had since she was a toddler. Holding the bear, the space around her felt colder, as if the air had been sucked out of the room.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion rattled. 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 rattled stories, after denoising with neutral dialogue baselines, produces the rattled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the rattled vector is projected through the unembedding matrix.

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234