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).

"Unbelievable," Michael whispered, his voice barely audible above the hum of the air conditioning. The pay scale, carelessly left open on the communal computer, had revealed a truth he'd preferred to remain ignorant of. He stared at it, the numbers burning into his memory.

He abruptly stood up from his chair, knocking it over with a loud crash. He quickly righted it, his face flushed with embarrassment, then retreated to the quiet of the supply closet. He needed a moment.

The cramped space, usually a source of irritation, felt oddly comforting now. He leaned against the shelf, closing his eyes, trying to regain his composure. The injustice of it all was a sharp, stinging pain.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290