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).

Her voice was flat, devoid of emotion. "It's off." Lisa told her friend on the phone. "They cancelled." The news, delivered with a shrug and a forced smile, had felt like a punch to the gut. The party, a desperate attempt to feel connected, acknowledged, was suddenly irrelevant.

The thought of facing the empty space of her apartment, the silence that would engulf her now, brought a fresh wave of despair. She went to the window, staring out at the rain-swept streets, the city lights blurred into indistinguishable pools of color.

She felt a hollowness spreading through her, a void that seemed to consume everything. She let the phone fall from her hand, the plastic clattering on the table. It was over.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.427
S0.405
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255