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).

Michael drummed his fingers on the worn surface of his desk, the familiar rhythm a futile attempt at order. The news had spread like wildfire. A buyout. His whole career, all the late nights, the sacrifices… reduced to a line item. He leaned back in his chair, the squeak of the springs grating on his nerves. He watched a dust bunny tumble across the floor in the afternoon light.

He pictured his father, a carpenter, his hands always roughened and stained, a man of tangible results. What did he, Michael, have to show for it? Emails, spreadsheets, presentations. A sense of purpose, yes, once. Now… a hollow echo. He felt a deep ache inside, an unsettling mix of sadness and bewilderment.

His stomach twisted into a knot. He’d planned on using his bonus for a down payment on a new car. Now, who knew what the future would hold? He rubbed his temples, trying to ward off a headache. The office felt suddenly cramped, the air thick with unspoken anxieties.

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