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 sat on the park bench, watching children chase pigeons. The sunlight felt odd, too bright, as if filtered through a distorted lens. The nurse's admission hung in the air: “There’s been an administrative error.” A chill crawled up his spine, even though he was sweating. The diagnosis he’d been dreading was now someone else’s burden.

He ran a hand through his thinning hair, a gesture he’d repeated countless times that day. His own fears, once terrifyingly real, were now suddenly… abstract. An empty space opened up within him, where a monstrous thing had resided.

A young couple strolled past, arms entwined, laughing. He watched them, a strange ache in his chest. His own future, once so clear, was now a jumble of blurred possibilities. He pulled out a crumpled cigarette packet, then thought better of it, stuffing it back in his pocket.

Emotion: reflective

Cluster: Nostalgia / Reflection
PC1 (Valence): -1.27 Negative
PC2 (Disposition): -1.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.650
L0.547
如今0.402
H0.353
own0.319
Suppressed:
la-0.687
de-0.659
l-0.388
/-0.324
--0.320