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 news seemed to suck the color from everything. The vibrant office, the bright monitors, the cheerful banter of colleagues – all muted, drained of life. Sarah sank back in her chair, feeling a sinking sensation in her stomach. A heavy silence settled over her.

She stared at the screen, re-reading the email multiple times, hoping the words would change, that the message would somehow be different. But they never did. She felt a profound agitation, a restlessness that she couldn't quell.

She drummed her fingers on the desk, the rhythmic tapping a frantic counterpoint to her racing thoughts. She thought of the future, a future now shrouded in uncertainty. Her future. The thought sent a fresh wave of unease washing over her.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229