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).

Liam stared at the email, the screen blurring before his eyes. His coffee, forgotten, grew cold in its ceramic mug. He'd stumbled upon it while cleaning out his junk folder; the subject line, "New therapist in town." Then, the name – “Cassidy Blackwood, LCSW.” His stomach lurched, a cold, sickening sensation. The girl who once tied his shoelaces together and tripped him in the hallway, now, allegedly, helped people?

He rubbed his temples, a dull ache throbbing there. The air in his apartment suddenly felt thin, hard to breathe. He imagined the way she used to look at him, a cold, calculating gaze. Could she possibly have changed? Or was this some elaborate, twisted game? His fingers instinctively reached for his phone, then retracted. He was dizzy with a mix of dread and morbid curiosity.

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