Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress

Genome engineering has achieved sequence-level precision, yet predicting the transcriptomic state a cell will occupy after perturbation remains open. Single-cell CRISPR screens measure how far cells move, but effect magnitude ignores whether the cells move together. We introduce Shesha perturbation stability ($S_p$), which quantifies directional coherence as the mean cosine similarity between individual cell shift vectors and the mean perturbation direction. Across five CRISPR datasets (2,200+ perturbations), stability correlates with magnitude (Spearman $\rho =0.75$–$0.97$), but discordant cases expose regulatory architecture: pleiotropic regulators such as CEBPA pay a ``geometric tax,‘’ producing large but incoherent shifts, while lineage-specific factors such as KLF1 produce coordinated responses. $S_p$ and Song et al.'s perturbation-response score (PS) share partial overlap (${\rho }_{\text{partial}}=+0.51$ after controlling for magnitude), but $S_p$ provides significant incremental prediction of UPR pathway activation beyond both PS and magnitude ($p<{10}^{-18}$). In a split-half reproducibility assay, $S_p$ predicts directional reproducibility beyond magnitude (${\rho }_{\text{partial}}=+0.384$) while PS does not (${\rho }_{\text{partial}}=-0.193$), with the advantage consistent across all magnitude strata and both datasets. Geometric instability is independently associated with UPR activation across four datasets. $S_p$ is implemented in the open-source shesha-geometry Python package.