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 attic felt stifling, the dust motes dancing in the single shaft of sunlight. Maria unfolded the brittle paper. It was a letter from her stepmother, a woman she'd barely known, written just before she died. A letter of resignation from a job Maria hadn't even known she'd held.

The words were cold, detached. Her stepmother spoke of feeling used, abused by a company and a man. Maria felt a sudden chill, despite the heat of the attic. She didn't know how to process this new information.

She pictured her stepmother's face, a face she'd only seen in photographs. She wasn't sure what to think, what to feel. She felt disoriented, like she was standing on shifting sand.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256