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 day stretched before Maya like an endless, unpaved road. She was restless. She went to retrieve the mail, hoping for a distraction from the dull ache inside her. Junk, mostly. Advertisements for things she didn’t want. Then, a single, unassuming card. "Happy Birthday!" it announced. No signature.

A sudden, sharp pang of something she couldn't name hit her. She felt oddly compelled to find the sender. The thought immediately brought with it another thought: what a waste of time. She tossed the card onto the table. The silence of the apartment felt suffocating. She grabbed the remote, flipping through channels, a futile search for something, anything, to capture her attention.

Her eyes drifted to the unopened card. She felt her chest tighten a little, then she opened it, just because.

Emotion: bored

Cluster: Fatigue / Lethargy
PC1 (Valence): 0.04 Positive
PC2 (Disposition): -1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.387
’0.350
unremarkable0.325
दिलचस्प0.323
seemingly0.319
Suppressed:
B-0.592
P-0.304
because-0.292
因为它-0.287
ancar-0.278