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).

"Just… just look at it," Sarah mumbled, pushing the paper across the table towards her roommate. Her voice was barely audible, her throat tight with a feeling of being near to tears. The paper, once a symbol of her intellectual work, now felt like a lead weight in her possession.

Her hands shook as she reached for her water bottle, spilling a few drops. The icy liquid didn't offer any relief to the fire blazing in her cheeks. She felt trapped, encircled. All her previous confidence had evaporated, leaving behind a residue of vulnerability and fear.

Her head throbbed. She struggled to keep the tears at bay, desperately wishing she could just disappear. She needed someone, anyone, to believe her.

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