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 sleek, black envelope felt incongruous in Michael's cluttered garage. He held it up to the light, the raised lettering catching the afternoon sun. "Northwood High - 20 Year Reunion." He knew he should be excited. He'd been successful, he had everything he'd ever wanted. Yet, he didn’t feel that way.

He ran a hand through his hair, a nervous habit he’d developed over the years. The memories flooded back: the pressure, the competition, the constant need to prove himself. The garage door creaked as he slammed it shut. He felt a sudden, overwhelming urge to run.

He went inside and grabbed a beer, the icy bottle offering only a temporary distraction. The reunion. He was sure he’d go. But the thought left a lingering ache in his chest.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284