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 low hum of the fluorescent lights in the shared laundry room amplified the simmering argument. Sarah felt a prickling sensation across her scalp. Mark was refusing, flat out, to even *consider* the shelter dogs. Her shoulders were bunched, as if shielding her from an impending blow.

"It's about responsibility," he'd said, his voice clipped and decisive. "A dog is a commitment. For years." She felt the heat rising in her cheeks, a flush that mirrored the fiery resentment building inside her.

She folded a towel with unnecessary force, the fabric bunching in her fists. The thought of another day like this – with the apartment echoing with his silence and her mounting disappointment – was almost unbearable.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198