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).

He paced the living room, the worn carpet offering little comfort beneath his bare feet. The silence of the house, usually a solace, now pressed in on him. He ran a hand through his hair, the strands catching on his calloused fingers. The stale air hung thick, a suffocating reminder of his inertia.

“Anything on the job front?” his mother had asked earlier, her voice gentle, but her words a subtle pressure. He’d mumbled a response, something about “sending out applications.” He knew the disappointment in her eyes. It was a mirror of his own self-loathing.

He stopped pacing, staring out the window at the familiar street. The world moved on, oblivious to the storm raging inside him. He felt adrift, untethered, a ghost in his own life.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236