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 chipped mug warmed Amelia's hands, but did little to thaw the cold that had settled in her chest. Days blurred into weeks, each a monotonous echo of the last. She hadn’t touched her paints in months, the canvases in her studio gathering dust, mirroring the stagnation in her own life. Then, a friend called, excitedly gushing about a new gallery exhibit downtown. "You *have* to see it," she’d insisted. "It's incredible." Amelia almost declined, but the curiosity, a tiny flicker of something akin to hope, compelled her to go.

The gallery buzzed with people, wine glasses clinking. She drifted through the crowd, feeling invisible. Then she saw it: a vibrant, explosive painting, her painting. The brushstrokes, the colors – it was unmistakably hers. But the nameplate bore another name. A wave of nausea washed over her. She felt like a phantom, her creation stolen and celebrated, while she remained unseen, unheard.

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